Open Chinese LLM - GSM8K: leaderboard
The "GSM8K" subtask of Open Chinese LLM. A task from the Open Chinese LLM Leaderboard, evaluating models on Chinese-language knowledge, reasoning and understanding.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 339 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2 72B Instruct | 78.7 | #576 |
| 2 | Qwen 2 72B | 75.36 | #521 |
| 3 | Llama3-TenyxChat-70B | 72.71 | #735 |
| 4 | Le_Triomphant-ECE-TW3 | 71.57 | #559 |
| 5 | dolphin-2.9.1-llama-3-70B | 70.96 | #722 |
| 6 | Llama 3 70B Japanese Suzume Vector V0.1 | 70.58 | #765 |
| 7 | YiSM-34B-0rn | 70.36 | #709 |
| 8 | free-evo-qwen72B-v0.8-re | 70.28 | #435 |
| 9 | Rhea-72B-v0.5 | 70.2 | #556 |
| 10 | Smaug-72B-v0.1 | 70.13 | #611 |
| 11 | YiSM-blossom5.1-34B-SLERP | 70.13 | #591 |
| 12 | Smaug-Llama-3-70B-Instruct | 70.05 | #716 |
| 13 | Qwen 2 57B A14B Instruct | 69.29 | #748 |
| 14 | autotrain-llama3-70B-orpo-v1 | 68.84 | #828 |
| 15 | Yi 1.5 34B Chat | 68.31 | #800 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=open-chinese-llm-gsm8k · How It Works · Data refreshed daily, snapshot 2026-10-20.